Pith. sign in

REVIEW 4 cited by

Imitation Learning via Off-Policy Distribution Matching

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1912.05032 v1 pith:DKLH5HVT submitted 2019-12-10 cs.LG stat.ML

classification cs.LGstat.ML
keywords distributionobjectiveimitationlearningalgorithmestimationmannermatching
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

When performing imitation learning from expert demonstrations, distribution matching is a popular approach, in which one alternates between estimating distribution ratios and then using these ratios as rewards in a standard reinforcement learning (RL) algorithm. Traditionally, estimation of the distribution ratio requires on-policy data, which has caused previous work to either be exorbitantly data-inefficient or alter the original objective in a manner that can drastically change its optimum. In this work, we show how the original distribution ratio estimation objective may be transformed in a principled manner to yield a completely off-policy objective. In addition to the data-efficiency that this provides, we are able to show that this objective also renders the use of a separate RL optimization unnecessary.Rather, an imitation policy may be learned directly from this objective without the use of explicit rewards. We call the resulting algorithm ValueDICE and evaluate it on a suite of popular imitation learning benchmarks, finding that it can achieve state-of-the-art sample efficiency and performance.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Distributional Inverse Reinforcement Learning

    cs.LG 2025-10 unverdicted novelty 6.0 of 10

    DistIRL recovers reward distributions and risk-aware policies from offline demonstrations by minimizing first-order stochastic dominance violations between agent and expert returns.

  2. Value from Observations: Towards Large-Scale Imitation Learning via Self-Improvement

    cs.LG 2025-07 conditional novelty 6.0 of 10

    VfO trains a state-value function on action-free expert demonstrations mixed with lower-quality background data, then uses advantage-weighted regression on the background data to improve the agent, approaching oracle ...

  3. Exploration from a Primal-Dual Lens: Value-Incentivized Actor-Critic Methods for Sample-Efficient Online RL

    cs.LG 2025-06 conditional novelty 6.0 of 10

    VAC is a new actor-critic method with a single optimistic objective and a provably near-optimal regret bound in linear Markov decision processes.

  4. Diffusion-Modeled Reinforcement Learning for Carbon and Risk-Aware Microgrid Optimization

    cs.LG 2025-07 reject novelty 4.0 of 10

    DiffCarl, a diffusion-actor variant of SAC with carbon pricing and CVaR risk terms, is reported to lower microgrid operating cost by 2.3-30.1% versus baselines, though the paper's own numbers contradict its 28.7% carb...

Pith tools